INDEX
Explanations
terms related to political controversies and international relations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
478
+0.10
0.3%
1385
+0.10
0.3%
303
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
303
+0.10
0.04
1244
+0.10
0.03
332
+0.09
0.03
Negative Logits
hasData
-0.61
CONDU
-0.55
AssemblyProduct
-0.53
imageshack
-0.53
eably
-0.52
DoubleQuotes
-0.51
EndContext
-0.49
POLLUTION
-0.48
Handlung
-0.48
endroits
-0.47
POSITIVE LOGITS
tph
0.96
lts
0.93
colombia
0.92
venezuela
0.92
santiago
0.91
tenerife
0.84
fta
0.84
guatemala
0.84
jorge
0.84
encomp
0.83
Activations Density 0.173%